Author
Sarah Welsh
Recent posts
-
Prompt EngineeringDSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines
Introduction Chaining language model (LM) calls as composable modules is fueling a new way of programming, but ensuring LMs adhere to important constraints requires heuristic “prompt engineering.” The… Sarah Welsh July 24, 2024 30 min read -
AI EngineeringRAFT: Adapting Language Model to Domain Specific RAG
Introduction Where adapting LLMs to specialized domains is essential (e.g., recent news, enterprise private documents), we discuss a paper that asks how we adapt pre-trained LLMs for RAG… Sarah Welsh June 28, 2024 38 min read -
AI EngineeringLLM Interpretability and Sparse Autoencoders: Research from OpenAI and Anthropic
Introduction It’s been an exciting couple weeks for GenAI! Join us as we discuss the latest research from OpenAI and Anthropic. We’re excited to chat about this significant… Sarah Welsh June 14, 2024 43 min read -
AI EvaluationTrustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment
Introduction We break down a paper, Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment. Ensuring alignment (aka: making models behave in accordance with human… Sarah Welsh May 29, 2024 41 min read -
AI EvaluationBreaking Down EvalGen: Who Validates the Validators?
Introduction Due to the cumbersome nature of human evaluation and limitations of code-based evaluation, Large Language Models (LLMs) are increasingly being used to assist humans in evaluating LLM… Sarah Welsh May 13, 2024 38 min read -
Agent EngineeringKeys To Understanding ReAct: Synergizing Reasoning and Acting in Language Models
Introduction This week we explore ReAct, an approach that enhances the reasoning and decision-making capabilities of LLMs by combining step-by-step reasoning with the ability to take actions and… Sarah Welsh April 26, 2024 39 min read -
AI EngineeringDemystifying Amazon’s Chronos: Learning the Language of Time Series
Introduction This week, we’ve covering Amazon’s time series model: Chronos. Developing accurate machine-learning-based forecasting models has traditionally required substantial dataset-specific tuning and model customization. Chronos however, is built… Sarah Welsh April 4, 2024 36 min read -
AI EngineeringAnthropic Claude 3
Introduction In this week’s Arize Community Paper Reading we dive into the latest buzz in the AI world—the arrival of Claude 3. Claude 3 is the newest family… Sarah Welsh March 25, 2024 38 min read -
AI EngineeringReinforcement Learning in the Era of LLMs
Introduction This week, we explore Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond, with Claire… Sarah Welsh March 15, 2024 38 min read -
AI EngineeringSora: OpenAI’s Text-to-Video Generation Model
Introduction This week, we talk about the implications of Text-to-Video Generation and speculate as to the possibilities (and limitations) of this incredible technology with some hot takes. Dat… Sarah Welsh March 1, 2024 37 min read
Don’t ship vibes.
Arize gives AI teams observability and evals to understand and improve agent performance.
